memory_write

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations, so the description carries the full burden. It does disclose two useful behaviors: the return value (the note's id) and the supersession semantics ('pass supersedes to replace an older note'). It says nothing about permissions, durability, deduplication, or whether superseding makes the old note unreadable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and purpose, then the return value, then the one non-obvious parameter behavior. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists and the description still confirms the id return, and all four parameters are schema-documented. Adequate for a write tool, though lifecycle details (what superseding does to the old note, whether notes persist) remain unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented (body size cap, tag charset, supersedes meaning). The description only restates the supersedes intent, adding no format or constraint detail beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb+resource ('Save a note') plus the kinds of content the note holds (decision, finding, convention) and the destination (other agents on this project). It reads clearly as the write counterpart to memory_read/memory_search, but it never names a sibling to sharpen the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives practical when-to-use context by enumerating the note categories (decision, finding, convention) and implying a shared, cross-agent audience. It stops short of explicit alternatives or exclusions, e.g. when to prefer handoff_create or how it relates to memory_read.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.